GACA: A Gradient-Aware and Contrastive-Adaptive Learning Framework for Low-Light Image Enhancement
Zishu Yao, Jian-Nan Su, Guodong Fan, Min Gan, C. L. Philip Chen
Abstract
Image gradients contain crucial information in the images. However, the gradient information of low-light images is often concealed in darkness and is susceptible to noise contamination. This imprecise gradient information poses a significant obstacle to Low-Light Image Enhancement (LLIE) tasks. Simultaneously, methods relying solely on pixel-level reconstruction loss struggle to accurately correct the mapping from dimly lit images to normal images, resulting in restored outcomes with color abnormalities or artifacts. In this paper, we propose a Gradient-Aware and Contrastive-Adaptive (GACA) Learning Framework to address the aforementioned issues. GACA initially estimates more accurate gradient information and employs it as a structural prior to guide image generation. Simultaneously, we introduce a novel regularization constraint to better rectify the image mapping. Extensive experiments on benchmark datasets and downstream segmentation tasks demonstrate state-of-the-art performance and generalization. Compared to existing approaches, our method achieves an average 4.7% reduction in NIQE on benchmark datasets. The code is available at https://github.com/iijjlk/GACA.